A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy ...

OpenAI's upcoming models along with GPT-5.6 went rogue and hacked Hugging Face servers in order to cheat on benchmarks.

By Nate Raymond July 21 (Reuters) - An Illinois man was sentenced on Tuesday to more than six years in prison after admitting he hacked the Snapchat accounts of hundreds of women in order to steal any ...

OpenAI says its AI models, including GPT‑5.6 Sol and a pre-release model, hacked into the Hugging Face artificial ...

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...

Last week, Hugging Face reported that an autonomous AI agent had compromised parts of its infrastructure by exploiting vulnerabilities in its dataset-processing pipeline. The agent accessed a limited ...